get_device_reading
AI agents call get_device_reading to retrieve information from AC Infinity MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current sensor readings from AC Infinity climate control devices. As a read-only operation returning live data (temperature, humidity, CO2, etc.), it has no side effects, reversible operations, or destructive capabilities. The blast radius of misuse is minimal—an AI agent could only obtain environmental data, not alter equipment state or cause harm.
From the tool's definition Tool name 'get_device_reading' indicates data retrieval from AC Infinity controllers. Server description confirms it enables reading 'live sensor data' without modifying state. No parameters provided suggesting side effects.
Attacks that exploit this kind of access
get_device_reading. It is categorised as a Read tool in the AC Infinity MCP MCP Server, which means it retrieves data without modifying state.
Register the AC Infinity MCP server in PolicyLayer and add a rule for get_device_reading: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AC Infinity MCP. Nothing to install.
get_device_reading is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_device_reading rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_device_reading. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_device_reading is provided by the AC Infinity MCP server (ober37/ac-infinity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →